Frequency-domain blind quality assessment of blurred and blocking-artefact images using Gaussian Process Regression model
作者：
Highlights：
• Lack of Image quality assessment methods for multiply distorted visual media.
• Blurriness and Blockiness are two interdependent distortions that go hand in hand.
• Method is proposed to detect blockiness and blurriness independently and jointly.
• It uses Divisive normalization and Discrete Fourier Transform to assess quality.
• Gives superior performance in correlation with Human Visual system.
摘要
•Lack of Image quality assessment methods for multiply distorted visual media.•Blurriness and Blockiness are two interdependent distortions that go hand in hand.•Method is proposed to detect blockiness and blurriness independently and jointly.•It uses Divisive normalization and Discrete Fourier Transform to assess quality.•Gives superior performance in correlation with Human Visual system.
论文关键词：Image quality assessment,Multiple distortions,Blocking artefacts,Blurriness,Discrete Fourier Transform
论文评审过程：Received 23 December 2020, Revised 23 January 2022, Accepted 24 January 2022, Available online 31 January 2022, Version of Record 15 February 2022.
论文官网地址：https://doi.org/10.1016/j.image.2022.116651
